Application of a light-weighted convolutional neural network for automatic recognition of coal workers' pneumoconiosis in the early stage / 中华劳动卫生职业病杂志

Objective: To construct and verify a light-weighted convolutional neural network (CNN), and explore its application value for screening the early stage (subcategory 0/1 and stage Ⅰ of pneumoconiosis) of coal workers' pneumoconiosis (CWP) from digital chest radiography (DR) . Methods: A total of 1225 DR images of coal workers who were examined at an Occupational Disease Prevention and Control Institute in Anhui Province from October 2018 to March 2021 were retrospectively collected. All DR images were collectively diagnosed by 3 radiologists with diagnostic qualifications and gave diagnostic results. There were 692 DR images with small opacity profusion 0/- or 0/0 and 533 DR images with small opacity profusion 0/1 to stage Ⅲ of pneumoconiosis. The original chest radiographs were preprocessed differently to generate four datasets, namely 16-bit grayscale original image set (Origin16), 8-bit grayscale original image set (Origin 8), 16-bit grayscale histogram equalized image set (HE16) and 8-bit grayscale histogram equalized image set (HE8). The light-weighted CNN, ShuffleNet, was applied to train the generated prediction model on the four datasets separately. The performance of the four models for pneumoconiosis prediction was evaluated on a test set containing 130 DR images using measures such as the receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, and Youden index. The Kappa consistency test was used to compare the agreement between the model predictions and the physician diagnosed pneumoconiosis results. Results: Origin16 model achieved the highest ROC area under the curve (AUC=0.958), accuracy (92.3%), specificity (92.9%), and Youden index (0.8452) for predicting pneumoconiosis, with a sensitivity of 91.7%. And the highest consistency between identification and physician diagnosis was observed for Origin16 model (Kappa value was 0.845, 95%CI: 0.753-0.937, P<0.001). HE16 model had the highest sensitivity (98.3%) . Conclusion: The light-weighted CNN ShuffleNet model can efficiently identify the early stages of CWP, and its application in the early screening of CWP can effectively improve physicians' work efficiency.

Investigation about prevention behavior for dust workers in machinery, ceramic, and metallurgy industry / 中华劳动卫生职业病杂志

<p><b>OBJECTIVE</b>The purposes of this thesis were to study the behavior about workers exposed to dust and provide scientific basis for health promotion.</p><p><b>METHODS</b>We designed a questionnaire and carry it on the 746 dust workers in the 3 representative corporations of Machinery, Ceramic, and Metallurgy Industry. All data were input into computer. And a database was established with Excel. SPSS11.5 statistical analysis software was used to analyze the influence on protecting behavioral between the application of qualifications, different jobs, training or protection, and other aspects etc.</p><p><b>RESULTS</b>The rates were 94.4% and 75.3% about the regular physical examination and requirements for protective equipment. The rate of choosing an effective way of protection was generally low (15.4%). There was significant difference for among different educational background workers (P < 0.01). The rates of choosing an effective way of protection (20.3%), the regular physical examination (98.3%) and requirements for protective equipment (86.4%) in the dust workers who participated in the training of dust protection were superior than those who did not participated in the training. There was the significant difference (P < 0.05, P < 0.01). There was the significant difference for the rate of effective way of protection, regular physical examination, and requirements for protective equipment among the different corporations (P < 0.05).</p><p><b>CONCLUSIONS</b>Dust workers' using rate about the choosing an effective way of protection was generally low in Machinery, Ceramic, and Metallurgy Industry. Those who were not educated had a lower using rate about the protection behavior, regular physical examination, and requirements for protective equipment than those educated.</p>